Publications

Grönroos, Stig-Arne; Jokinen, Kristiina; Hiovain, Katri; Kurimo, Mikko; Virpioja, Sami
Low-Resource Active Learning of North Sami Morphological Segmentation.
1st International Workshop on Computational Linguistics for Uralic Languages. 20-33.
Elektroninen julkaisu   http://dx.doi.org/10.7557/5.3465 
Avainsanat: morphological segmentation, morfessor, active learning, low resource, north sami


Virpioja, Sami; Grönroos, Stig-Arne
LeBLEU: N-gram-based Translation Evaluation Score for Morphologically Complex Languages.
The Tenth Workshop on Statistical Machine Translation (WMT15); Lisbon, Portugal, 17-18 September. 2015, Association for Computational Linguistics, 411-416.
Elektroninen julkaisu   http://www.statmt.org/wmt15/pdf/WMT52.pdf 
Avainsanat: statistical machine translation, morphology, evaluation, fuzzy matching


Grönroos, Stig-Arne; Virpioja, Sami; Kurimo, Mikko
Tuning Phrase-Based Segmented Translation for a Morphologically Complex Target Language.
The Tenth Workshop on Statistical Machine Translation (WMT15); Lisbon, Portugal, 17-18 September. 2015, Association for Computational Linguistics, 105-111.
Elektroninen julkaisu   http://www.statmt.org/wmt15/pdf/WMT10.pdf 
Avainsanat: statistical machine translation, morphological segmentation, morfessor, neural language model


Lautenbacher, Olli-Philippe; Tiittula, Liisa; Hirvonen, Maija; Laaksonen, Jorma; Kurimo, Mikko
Towards Reliable Automatic Multimodal Content Analysis.
2015 Conference on Empirical Methods for Natural Language Processing, Fourth Workshop on Vision and Language. Lisbon, Portugal 2015, Association for Computational Linguistics, 6-7.
Elektroninen julkaisu   https://www.cs.cmu.edu/~ark/EMNLP-2015/proceedings/VL/pdf/VL03.pdf 


Remes, Ulpu; Ramirez Lopez, Ana; Palomäki, Kalle; Kurimo, Mikko
Bounded conditional mean imputation with observation uncertainties and acoustic model adaptation.
IEEE/ACM Transactions on Audio, Speech and Language Processing , 2015. Vol. 23, nro 7, 1198-1208.
Elektroninen julkaisu   http://dx.doi.org/10.1109/TASLP.2015.2424322 


Ramirez Lopez, Ana; Ono, Nobutaka; Remes, Ulpu; Palomäki, Kalle; Kurimo, Mikko
Designing multichannel source separation based on single-channel source separation.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. unknown 2015,


Gowda, Dhananjaya; Saeidi, Rahim; Alku, Paavo
AM-FM based filter bank analysis for estimation of spectro-temporal envelopes and its application for speaker recognition in noisy reverberant environments.
Interspeech’15, Dresden, Germany, Sept. 6-10, 2015.


Jokinen, Emma; Remes, Ulpu; Alku, Paavo
Comparison of Gaussian process regression and Gaussian mixture models in spectral tilt modelling for intelligibility enhancement of telephone speech.
Interspeech’15, Dresden, Germany, Sept. 6-10, 2015.


Kallasjoki, Heikki; Gemmeke, Jort; Palomäki, Kalle; Beeston, Amy; Brown, Guy
Recognition of reverberant speech by missing data imputation and NMF feature enhancement.
REVERB Workshop, Florence, Italy, May 10, 2014.
Elektroninen julkaisu   http://reverb2014.dereverberation.com/workshop/reverb2014-papers/1569899201.pdf 


Palomäki, Kalle; Kallasjoki, Heikki
Reverberation robust speech recognition by matching distributions of spectrally and temporally decorrelated features.
REVERB workshop, Florence Italy, May 10, 2014.
Elektroninen julkaisu   http://reverb2014.dereverberation.com/workshop/reverb2014-papers/1569899199.pdf 


Amid, Ehsan; Mesaros, Annamaria; Palomäki, Kalle J.; Laaksonen, Jorma; Kurimo, Mikko
Unsupervised Feature Extraction For Multimedia Event Detection And Ranking Using Audio Content.
IEEE international conference on acoustics, speech and signal processing, ICASSP, May 4-9, Florence, Italy.


Varjokallio, Matti; Kurimo, Mikko
A Word-Level Token-Passing Decoder for Subword n-gram LVCSR.
IEEE Spoken Language Technology Workshop (SLT 2014), December 7-10, 2014, South Lake Tahoe, Nevada, USA. 495-500.


Varjokallio, Matti; Kurimo, Mikko
A Toolkit for Efficient Learning of Lexical Units for Speech Recognition.
The 9th edition of the Language Resources and Evaluation Conference (LREC'14), Reykjavik, Iceland, 26 - 31 May, 2014. 2014, European Language Resources Association (ELRA),
Elektroninen julkaisu   http://www.lrec-conf.org/proceedings/lrec2014/pdf/715_Paper.pdf 


Raamadhurai, Srikrishna; Kohonen, Oskar; Ruokolainen, Teemu
Creating Custom Taggers by Integrating Web Page Annotation and Machine Learning.
25th International Conference on Computational Linguistics (COLING 2014): System Demonstrations, Dublin, Ireland, 23-29 August 2014.


Silfverberg, Miikka; Ruokolainen, Teemu; Linden, Krister; Kurimo, Mikko
Part-of-Speech Tagging using Conditional Random Fields: Exploiting Sub-Label Dependencies for Improved Accuracy.
Fifty-Second Annual Meeting of the Association for Computational Linguistics (ACL 2014), Baltimore, USA, 22-27 June 2014.


Ruokolainen, Teemu; Kohonen, Oskar; Virpioja, Sami; Kurimo, Mikko
Painless Semi-Supervised Morphological Segmentation using Conditional Random Fields.
Fourteenth Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), Gothenburg, Sweden, 26–30 April 2014.


Ruokolainen, Teemu; Silfverberg, Miikka; Kurimo, Mikko; Linden, Krister
Accelerated Estimation of Conditional Random Fields using a Pseudo-Likelihood-inspired Perceptron Variant.
Fourteenth Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), Gothenburg, Sweden, 26–30 April 2014.


Gowda, Dhananjaya; Kallasjoki, Heikki; Karhila, Reima; Contan, Cristian; Palomäki, Kalle; Giurgiu, Mircea; Kurimo, Mikko
On the role of missing data imputation and NMF feature enhancement in building synthetic voices using reverberant speech.
Interspeech-2014, Singapore, September 14-18, 2014. Singapore 2014, ISCA, 2947-2951.
Elektroninen julkaisu   http://www.isca-speech.org/archive/interspeech_2014/i14_2947.html 
Avainsanat: dereverberation, missing data imputation, nonnegative matrix factorization, GlottHMM, speech synthesis, speech enhancement
Tutkimusprojektin tiedot


Suni, Antti; Raitio, Tuomo; Gowda, Dhananjaya; Karhila, Reima; Gibson, Matt; Watts, Oliver
The Simple4All entry to the Blizzard Challenge 2014.
Blizzard Challenge 2014 Workshop, Singapore, September 19, 2014.


Smit, Peter; Virpioja, Sami; Grönroos, Stig-Arne; Kurimo, Mikko
Morfessor 2.0: Toolkit for statistical morphological segmentation.
The 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Gothenburg, Sweden, April 26-30, 2014.
Elektroninen julkaisu   http://www.aclweb.org/anthology/E/E14/E14-2006.pdf 
Avainsanat: morphological segmentation, morfessor


Grönroos, Stig-Arne; Virpioja, Sami; Smit, Peter; Kurimo, Mikko
Morfessor FlatCat: An HMM-Based Method for Unsupervised and Semi-Supervised Learning of Morphology.
The 25th International Conference on Computational Linguistics (COLING 2014); Dublin, Ireland, August 23-29. 2014, Dublin City University and Association for Computational Linguistics, 1177-1185.
Elektroninen julkaisu   http://www.aclweb.org/anthology/C/C14/C14-1111.pdf 
Avainsanat: morphological segmentation, morphotactics, hidden markov model


Jokinen, Emma; Remes, Ulpu; Takanen, Marko; Palomäki, Kalle; Kurimo, Mikko; Alku, Paavo
Spectral tilt modelling with extrapolated GMMs for intelligibility enhancement of narrowband telephone speech.
The International Workshop on Acoustic Signal Enhancement (IWAENC 2014), Antibes – Juan les Pins, France, Sept. 8-11, 2014.
Avainsanat: speech, GMM


Jokinen, Emma; Remes, Ulpu; Takanen, Marko; Palomäki, Kalle; Kurimo, Mikko; Alku, Paavo
Spectral tilt modelling with GMMs for intelligibility enhancement of narrowband telephone speech.
INTERSPEECH, Singapore, Sept. 14-18, 2014.
Avainsanat: speech, GMM


Heittola, Toni; Mesaros, Annamaria; Korpi, Dani; Eronen, Antti; Virtanen, Tuomas
Method for creating location-specific audio textures.
Eurasip journal on audio speech and music processing, 2014. Nro 9, 000009/1-13.


Karhila, Reima; Remes, Ulpu; Kurimo, Mikko
Noise in HMM-Based Speech Synthesis Adaptation: Analysis, Evaluation Methods and Experiments.
IEEE journal of selected topics in signal processing, 2014. Vol. 8, nro 2, pp. 285-295.


Kallasjoki, Heikki; Gemmeke, Jort F.; Palomaki, Kalle J.
Estimating Uncertainty to Improve Exemplar-Based Feature Enhancement for Noise Robust Speech Recognition.
Ieee-acm transactions on audio speech and language processing , 2014. Vol. 22, nro 2, pp. 368-380.
Avainsanat: Exemplar-based, noise robustness, observation uncertainty, speech recognition, uncertainty estimation.


Virpioja, Sami; Smit, Peter; Grönroos, Stig-Arne; Kurimo, Mikko
Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline.
Helsinki: Aalto University, 2013. 38 (Aalto University publication series SCIENCE + TECHNOLOGY 25/2013).
Elektroninen julkaisu   https://aaltodoc.aalto.fi/handle/123456789/11836 


Varjokallio, Matti; Kurimo, Mikko; Virpioja, Sami
Learning a Subword Vocabulary Based on Unigram Likelihood.
IEEE Automatic Speech Recognition and Understanding Workshop, (ASRU 2013), Olomouc, Czech Republic, December 8-12, 2013.


Yegnanarayana, Bayya; Gowda, Dhananjaya
Spectro-temporal analysis of speech signals using zero-time windowing and group delay function.
Speech Communication, 2013. Vol. 55, nro 6, pp. 782-795.


Turunen, Ville; Kurimo, Mikko; Keronen, Sami
Results for variable speaker and recording conditions on spoken IR in Finnish.
The 15th Internation Conference on Speech and Computer. Plze\v n 2013, pp. 271-277.


Suni, Antti; Karhila, Reima; Raitio, Tuomo; Kurimo, Mikko; Vainio, Martti; Alku, Paavo
Lombard Modified Text-to-Speech Synthesis for Improved Intelligibility: Submission for the Hurricane Challenge 2013.
Interspeech, (INTERSPEECH), Lyon, 25 August 2013 - 29 August 2013.


Ruokolainen, Teemu; Kohonen, Oskar; Virpioja, Sami; Kurimo, Mikko
Supervised Morphological Segmentation in a Low-Resource Learning Setting using Conditional Random Fields.
Seventeenth Conference on Computational Natural Language Learning (CoNLL), August 8-9, Sofia, Bulgaria. 2013, Association for Computational Linguistics, pp. 29-37.
Elektroninen julkaisu   http://www.aclweb.org/anthology/W13-3504 


Remes, Ulpu; Karhila, Reima; Kurimo, Mikko
Objective evaluation measures for speaker-adaptive HMM-TTS systems.
8th ISCA Speech Synthesis Workshop, (SSW8), Barcelona, 31 August 2013 - 2 September 3013. pp. 177-181.
Elektroninen julkaisu   http://ssw8.talp.cat/papers/ssw8_PS2-6_Remes.pdf 


Remes, Ulpu
Bounded conditional mean imputation with an approximate posterior.
Interspeech, (INTERSPEECH), Lyon, 25 August 2013 - 29 August 2013. pp. 3007-3011.


Prakash, Chetana; Gowda, Dhananjaya; Gangashetty, Suryakanth
Analysis of acoustic events in speech signals using Bessel series expansion.
Circuits, Systems, and Signal Processing, 2013. Vol. 32, nro 6, pp. 2915-2938.


Mesaros, Annamaria; Heittola, Toni; Palomäki, Kalle
Query-by-example retrieval of sound events using an integrated similarity measure of content and label.
14th International Workshop on Image and Audio Analysis for Multimedia Interactive services (WIA2MIS 2013),Paris, France, 3-5 July, 2013. pp. 1 - 4.


Mesaros, Annamaria; Heittola, Toni; Palomäki, Kalle
Analysis of acoustic-semantic relationship for diversely annotated real-world audio data.
38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP),Vancouver, Canada,May 26 - 31, 2013. pp. 813 - 817.


Mesaros, Annamaria
Singing Voice Identification and Lyrics Transcription for Music Information Retrieval.
7th Conference on Speech Technology and Human-Computer Dialogue (SpeD2013), Cluj-Napoca, Romania, October 16-19, 2013 . pp. 10.


Mansikkaniemi, Andre; Kurimo, Mikko
Unsupervised Topic Adaptation for Morph-based Speech Recognition.
Interspeech 2013. 2013, IOS Press, pp. 2693-2697.
Elektroninen julkaisu   http://www.interspeech2013.org/ 


Koskinen, Miika; Viinikanoja, Jaakko; Kurimo, Mikko; Klami, Arto; Kaski, Samuel; Hari, Riitta
Identifying fragments of natural speech from the listener's MEG signals.
Human Brain Mapping, 2013. Vol. 34, nro 6, pp. 1477-1489.
Elektroninen julkaisu   http://dx.doi.org/10.1002/hbm.22004  (First published online: 17 FEB 2012)
Avainsanat: auditory perception, decoding, encoding, machine learning, magnetoencephalography, signal processing, speech
Tutkimusprojektin tiedot


Keronen, Sami; Remes, Ulpu; Kallasjoki, Heikki; Palomäki, Kalle J.
Noise robust missing data mask estimation based on automatically learned features.
The 2nd CHiME Workshop on Machine Listening in Multisource Environments. Vancouver 2013, pp. 77-78.


Keronen, Sami; Kallasjoki, Heikki; Remes, Ulpu; Brown, Guy J.; Gemmeke, Jort F.; Palomäki, Kalle J.
Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment.
Computer Speech and Language, 2013. Vol. 27, nro 3, pp. 798-819.
Elektroninen julkaisu   http://dx.doi.org/10.1016/j.csl.2012.06.005 


Keronen, Sami; Cho, KyungHyun; Raiko, Tapani; Ilin, Alexander; Palomäki, Kalle J.
Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation.
The 38th International Conference on Acoustics, Speech and Signal Processing. Vancouver 2013, pp. 6729-6733.


Karhila, Reima; Remes, Ulpu; Kurimo, Mikko
HMM-based speech synthesis adaptation using noisy data: analysis and evaluation methods.
The 38th international Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013. pp. 6930-6934.


Ishikawa, Satoru; Koskela, Markus; Sjöberg, Mats; Laaksonen, Jorma; Oja, Erkki; Amid, Ehsan; Palomäki, Kalle; Mesaros, Annamaria; Kurimo, Mikko
PicSOM Experiments in TRECVID 2013.
TRECVID 2013 Workshop, Gaithersburg, USA, November 20-22, 2013. Gaithersburg 2013,


Heittola, Toni; Mesaros, Annamaria; Virtanen, Tuomas; Gabbouj, Moncef
Supervised model training for overlapping sound events based on unsupervised source separation.
38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP),Vancouver, Canada,May 26 - 31, 2013. pp. 8677 - 8681.


Gowda, Dhananjaya; Pohjalainen, Jouni; Kurimo, Mikko; Alku, Paavo
Robust formant detection using group delay function and stabilized weighted linear prediction.
14th Annual Conference of the International Speech Communication Association, 25-29 August 2013, Lyon, France. pp. 49-53.


Gowda, Dhananjaya; Pohjalainen, Jouni; Alku, Paavo; Kurimo, Mikko
Robust spectral representation using group delay function and stabilized weighted linear prediction for additive noise degradations.
7th International Conference on Speech Technology and Human-Computer Dialogue (SpeD 2013), 16-19 Oct 2013, Cluj-Napoca, Romania. pp. 135-141.


Gowda, Dhananjaya; Kurimo, Mikko
Analysis of breathy, modal and pressed phonation based on low frequency spectral density.
14th Annual Conference of the International Speech Communication Association, 25-29 August 2013, Lyon, France. pp. 3206-3210.


Enarvi, Seppo; Kurimo, Mikko
Studies on Training Text Selection for Conversational Finnish Language Modeling.
10th International Workshop on Spoken Language Translation, (IWSLT 2013), Heidelberg, 5 Dec 2013 - 6 Dec 2013.


Enarvi, Seppo; Kurimo, Mikko
A Novel Discriminative Method for Pruning Pronunciation Dictionary Entries.
7th International Conference on Speech Technology and Human-Computer Dialogue, (SpeD 2013), Cluj-Napoca, 16 Oct 2013 - 19 Oct 2013. pp. 113-116.


Dines, John; Liang, Hui; Saheer, Lakshmi; Gibson, Matthew; Byrne, William; Oura, Keiichiro; Tokuda, Keiichi; Yamagishi, Junichi; King, Simon; Wester, Mirjam; Hirsim\äki, Teemu; Karhila, Reima; Kurimo, Mikko
Personalising speech-to-speech translation: unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis.
Computer, Speech & Language, 2013. Vol. 27, nro 2, pp. 420-437.
Elektroninen julkaisu   http://dx.doi.org/10.1016/j.csl.2011.08.003 


Dikmen, Onur; Mesaros, Annamaria
Sound Event Detection Using Non-negative Dictionaries Learned From Annotated Overlapping Events.
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2013), New Paltz, NY, October 20-23, 2013. pp. 4.
Elektroninen julkaisu   http://users.ics.aalto.fi/dikmen/waspaa13/waspaa13dikmen.pdf 


Virpioja, Sami
Learning Constructions of Natural Language: Statistical Models and Evaluations.
Espoo, Finland 2012, Aalto University School of Science. 437
Elektroninen julkaisu   http://urn.fi/URN:ISBN:978-952-60-4883-3 


Gemmeke, Jort F.; Remes, Ulpu
Missing-Data Techniques: Feature Reconstruction.
In: Virtanen, Tuomas; Singh, Rita; Raj, Bhiksha, Techniques for Noise Robustness in Automatic Speech Recognition. United Kingdom 2012, JOHN WILEY & SONS, pp. 399-432.
Elektroninen julkaisu   http://dx.doi.org/10.1002/9781118392683 


Virpioja, Sami; Paukkeri, Mari-Sanna; Tripathi, Abhishek; Lindh-Knuutila, Tiina; Lagus, Krista
Evaluating Vector Space Models with Canonical Correlation Analysis.
Natural Language Engineering, 2012. Vol. 18, nro 3, pp. 399-436.
Elektroninen julkaisu   http://dx.doi.org/10.1017/S1351324911000271 


Virpioja, Sami
Evaluation Methods for Unsupervised Natural Language Learning.
Federated Computer Science Event 2012, Helsinki, Finland, May 28-29, 2012. Helsinki 2012, Department of Computer Science, University of Helsinki, pp. 66-67.


Ruokolainen, Teemu
Applying Piecewise Approximation in Perceptron Training of Conditional Random Fields.
IDA Intelligent Data Analysis (IDA 2012) IDA, Helsinki, Finland, October 25-27, 2012. pp. 324-333.
Elektroninen julkaisu   http://link.springer.com/chapter/10.1007/978-3-642-34156-4_30 


Pylkkönen, Janne; Kurimo, Mikko
Analysis of Extended Baum-Welch and Constrained Optimization for Discriminative Training of HMMs.
IEEE Transactions on Audio, Speech, and Language Processing, 2012. Vol. 20, nro 9, pp. 2409-2419.


Pylkkönen, Janne; Kurimo, Mikko
Improving Discriminative Training for Robust Acoustic Models in Large Vocabulary Continuous Speech Recognition.
13th Annual Conference of the International Speech Communication Association (Interspeech 2012), Portland, Oregon, United States, September 10-13, 2012. pp. 1-4.


Pylkkönen, Janne; Kurimo, Mikko
Optimization-Based Control for the Extended Baum-Welch Algorithm.
INTERSPEECH 13th Annual Conference of the International Speech Communication Association (Interspeech 2012) INTERSPEECH, Portland, Oregon, United States, September 10-13, 2012. pp. 1-4.


Mansikkaniemi, Andre; Kurimo, Mikko
Unsupervised Vocabulary Adaptation for Morph-Based Language Models.
NAACL 2012 Workshop on the Future of Language Modeling for HLT, Montreal, Quebec, Canada, June 8, 2012. 2012, ACL, pp. 37-40.
Elektroninen julkaisu   https://sites.google.com/site/wlm2012naacl/home 


Mansikkaniemi, Andre; Kurimo, Mikko
Adaptation of Morpheme-based Speech Recognition for Foreign Entity Names, HLT 2012.
Fifth International Conference Human Language Technologies - The Baltic Perspective, Tartu, Estonia, October 4-5,2012. 2012, IOS Press, pp. 129-137.
Elektroninen julkaisu   http://www.cl.ut.ee/HLT2012/ 


Karhila, Reima; Doddipatla, Rama Sanand; Kurimo, Mikko; Smit, Peter
Creating synthetic voices for children by adapting adult average voice using stacked transformations and VTLN.
ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 25-30, 2012. Kyoto 2012, IEEE,
Elektroninen julkaisu   http://dx.doi.org/10.1109/ICASSP.2012.6288918 


Brown, Guy J.; Beeston, Amy; Palomäki, Kalle J.
Perceptual compensation for the effects of reverberation on consonant identification: A comparison of human and machine performance.
INTERSPEECH 13th Annual Conference of the International Speech Communication Association (INTERSPEECH) INTERSPEECH, Portland, Oregon, September 9-13, 2012. Portland 2012, pp. 1-4.


Pulakka, Hannu; Remes, Ulpu; Yrttiaho, Santeri; Palomäki, Kalle; Kurimo, Mikko; Alku, Paavo
Bandwidth extension of telephone speech to low frequencies using sinusoidal synthesis and Gaussian mixture model.
IEEE Transactions on Audio, Speech and Language Processing, 2012. Vol. 20, nro 8, 2219-2231.
Elektroninen julkaisu   http://dx.doi.org/10.1109/TASL.2012.2199110 
Avainsanat: speech

Page content by: | Last updated: 04.01.2016.